skills/steipete/openclaw/crabbox/Gen Agent Trust Hub

crabbox

Pass

Audited by Gen Agent Trust Hub on Jul 13, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands on remote environments via the crabbox and blacksmith CLI tools. This includes running tests, managing Docker containers, and performing CI-parity checks, which is the stated primary purpose of the tool.
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions to install the crabbox CLI from a vendor-owned Homebrew tap (openclaw/tap/crabbox). This is a standard installation procedure for the vendor's tooling.
  • [CREDENTIALS_UNSAFE]: The documentation references authentication via a coordinator token (CRABBOX_COORDINATOR_TOKEN) and describes a secure method of piping the environment variable into the login command rather than hardcoding credentials.
  • [DATA_EXFILTRATION]: Network operations are directed towards the vendor's coordinator API (crabbox.openclaw.ai) and established infrastructure providers (AWS, Hetzner, Blacksmith). No unauthorized or suspicious data exfiltration patterns were identified.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 13, 2026, 02:11 PM
Security Audit — agent-trust-hub — crabbox